after unclean shutdown my ceph cluster has some errors, and some of this errors can't be fixed by "ceph pg repair"
thats what i seen in log:
cluster [ERR] deep-scrub 1.774 24ac1774/rbd_data.511d802ae8944a.0000000000006285/head//1 on disk size (4194304) does not match object info size (2113536)...